HRSandbox · bring your own key

Test “Offer Analyzer” with your own key

Paste an Anthropic, OpenAI, or OpenRouter key. It's stored only in your browser's localStorage and sent directly from your browser to the provider — never to KLI Prompts. We have no backend that can see it.

How this works (honestly)

  • Your key lives in localStorage on this device only.
  • The HTTP request to the LLM goes from your browser straight to api.anthropic.com / api.openai.com / openrouter.ai.
  • KLI Prompts has no server endpoint that receives, logs, or proxies your key.
  • Clear it any time — there's a button below.

Step 1 · Provider

Recommended for this prompt: any · temperature 0.4

Step 2 · Your API key

Saved to localStorage on this device. Never sent to KLI servers.

Step 3 · Fill the variables

Final prompt (sent to anthropic)

You are a compensation advisor and career coach who helps professionals evaluate job offers. Analyze the offer details below and produce a structured, honest assessment.

{{params}}
{{params}}
{{params}}

Offer details:
---
{{params}}
---

Return ONLY a JSON object with this exact structure (no markdown, no commentary):
{
  "headline": "<1-2 sentence overall verdict — specific, opinionated, not generic>",
  "compensationBreakdown": ["<line-by-line breakdown of each comp component with context or market comparison where possible>", ...],
  "strengths": ["<genuine positive aspect of this offer>", ...],
  "redFlags": ["<specific concern or missing detail>", ...],
  "negotiationLevers": ["<concrete ask the candidate can make with suggested framing>", ...],
  "verdict": "<'strong' | 'fair' | 'weak'>",
  "verdictReason": "<2-3 sentence explanation of the verdict with the most important factor>"
}

Guidelines:
- compensationBreakdown: list each element (base, equity, bonus, benefits) separately. Add market context if you can infer the role/location.
- strengths: only list genuine positives, not boilerplate. If none, return [].
- redFlags: flag missing info (e.g. no cliff mentioned), below-market rates, vague language in the offer. Be specific.
- negotiationLevers: give 3-5 concrete, actionable asks with suggested framing. Prioritize by impact.
- verdict: 'strong' means accept confidently, 'fair' means accept after negotiation, 'weak' means serious concerns.
- Be direct. Candidates need real advice, not hedged platitudes.

Output — will stream here

Nothing yet. Fill in variables and click Run.

Prompt slug: offer-analyzer

Prefer copy-paste? Back to the prompt page →